Alzheimer's and Dementia: iSTAGING Alliance: Machine learning reveals links between brain aging, whiteness disorders, amyloid protein burden and cognition.

Aging is a complex, multi-factor process that affects brain structure in a heterogeneic way.
neurodegenerative diseases are associated with the deposition of abnormal proteins in the brain, such as Alzheimer's disease (AD), which increases with age and can lead to neuron damage and loss.
but in the absence of protein lesions, aging itself may also be associated with synapses and neuromedal loss.
According to Magnetic Resonance Imaging (MRI), in the absence of known co-diseases, brain aging appears to be associated with gray mass loss and can be quantified by pattern analysis as a measure of "brain age", which can be somewhat separated from the atrophy pattern associated with neurodegenerative diseases.
from several studies, multiple risk factors may accelerate the process of brain aging, which can be manifested in accelerated cognitive decline.
brain aging and neurodegenerative atrophy are associated with cognitive impairments that affect memory and executive function, however, each person may affect different cognitive areas.
, for example, typical cerebral aging and isoemia of small blood vessels are associated with a deterioration in executive function and working memory.
AD is associated with abnormal deposits of tau in nerve fiber tangles (NFTs) and amyloid protein beta (A beta) in nerve plaques, which often leads to forgotten multi-sphere syndrome.
recent advances in machine learning and neuroimaging have made it possible to develop imaging markers that provide a summary measure of how an individual's brain structure or function deviates from a typical brain aging trajectory.
deviation from this model may reflect biological processes of disease or the ability to recover from age-related conditions.
The pattern of brain change spans multiple levels, such as brain aging, the burden of whiteness disease, and neurodegenerative characteristics, which capture heterogeneity between individuals, creating a multidimensional concept of aging-related diseases, each exhibiting unique patterns of brain change.
Most recently, researchers studied the relationship between typical aging brain atrophy patterns and Alzheimer's disease (AD), white disease, cognition, and AD neuropathology through machine learning in a large, unified magnetic resonance imaging database (11 studies; 10,216 subjects).
study, researchers calculated three brain signals: brain age, AD-like neurodegeneration, and white mass growth (WMHs).
the brain chart and revealed the relationship between these features and cognitive and AD molecular biomarkers.
results showed that WMHs were associated with advanced brain aging, AD-like atrophy, poor cognition, and AD neuropathology in subjects with mild cognitive impairment (MCI)/AD and cognitive normality (CN).
WMH volume was associated with brain aging and cognitive decline in CN subjects over a 10-year errage.
that WMHs were twice as likely to be positive for amyloid beta (A beta) after the age of 65.
, brain aging, AD-like atrophy, and WMHs were better cognitive predictors than age in MCI/AD.
, the study created a brain map that quantifies the trajectory of brain aging, allowing people to systematically evaluate individual brain aging patterns.